kleidiai : add SME2 f32 kernel (#24414)
* kleidiai : add SME2 f32 kernel * enable dynamic scheduling for SME2 f32 kernel
This commit is contained in:
@@ -638,6 +638,7 @@ function(ggml_add_cpu_backend_variant_impl tag_name)
|
||||
${KLEIDIAI_SRC}/kai/ukernels/matmul/matmul_clamp_f32_qai8dxp_qsi8cxp/
|
||||
${KLEIDIAI_SRC}/kai/ukernels/matmul/matmul_clamp_fp32_bf16p_bf16p/
|
||||
${KLEIDIAI_SRC}/kai/ukernels/matmul/matmul_clamp_f32_f16p_qsi4c32p/
|
||||
${KLEIDIAI_SRC}/kai/ukernels/matmul/matmul_clamp_f32_f32p_f32p/
|
||||
${KLEIDIAI_SRC}/kai/ukernels/matmul/pack/)
|
||||
|
||||
set(ARCH_FLAGS_TEMP "${ARCH_FLAGS}")
|
||||
@@ -687,9 +688,15 @@ function(ggml_add_cpu_backend_variant_impl tag_name)
|
||||
${KLEIDIAI_SRC}/kai/ukernels/matmul/matmul_clamp_fp32_bf16p_bf16p/kai_matmul_clamp_f32_bf16p2vlx2_bf16p2vlx2_2vlx2vl_sme2_mopa_asm.S
|
||||
${KLEIDIAI_SRC}/kai/ukernels/matmul/matmul_clamp_f32_f16p_qsi4c32p/kai_matmul_clamp_f32_f16p1vlx2_qsi4c32p4vlx2_1vlx4vl_sme2_mopa.c
|
||||
${KLEIDIAI_SRC}/kai/ukernels/matmul/matmul_clamp_f32_f16p_qsi4c32p/kai_matmul_clamp_f32_f16p1vlx2_qsi4c32p4vlx2_1vlx4vl_sme2_mopa_asm.S
|
||||
${KLEIDIAI_SRC}/kai/ukernels/matmul/matmul_clamp_f32_f32p_f32p/kai_matmul_clamp_f32_f32p2vlx1_f32p2vlx1biasf32_sme2_mopa.c
|
||||
${KLEIDIAI_SRC}/kai/ukernels/matmul/matmul_clamp_f32_f32p_f32p/kai_matmul_clamp_f32_f32p2vlx1_f32p2vlx1biasf32_sme2_mopa_asm.S
|
||||
${KLEIDIAI_SRC}/kai/ukernels/matmul/pack/kai_lhs_pack_bf16p2vlx2_f32_sme.c
|
||||
${KLEIDIAI_SRC}/kai/ukernels/matmul/pack/kai_rhs_pack_kxn_bf16p2vlx2b_f32_x32_sme.c
|
||||
${KLEIDIAI_SRC}/kai/ukernels/matmul/pack/kai_lhs_pack_f16pmrx2_f32_neon.c
|
||||
${KLEIDIAI_SRC}/kai/ukernels/matmul/pack/kai_lhs_pack_f32p2vlx1_f32_sme.c
|
||||
${KLEIDIAI_SRC}/kai/ukernels/matmul/pack/kai_lhs_pack_f32p2vlx1_f32_sme_asm.S
|
||||
${KLEIDIAI_SRC}/kai/ukernels/matmul/pack/kai_rhs_pack_nxk_f32p2vlx1biasf32_f32_f32_sme.c
|
||||
${KLEIDIAI_SRC}/kai/ukernels/matmul/pack/kai_rhs_pack_nxk_f32p2vlx1biasf32_f32_f32_sme_asm.S
|
||||
${KLEIDIAI_SRC}/kai/kai_common_sme_asm.S)
|
||||
set(PRIVATE_ARCH_FLAGS "-fno-tree-vectorize;${PRIVATE_ARCH_FLAGS}+sve+sve2+sme2+fp16")
|
||||
endif()
|
||||
|
||||
Reference in New Issue
Block a user